首页 | 本学科首页   官方微博 | 高级检索  
     

一种基于划分的动态聚类算法
引用本文:万志华,欧阳为民,张平庸. 一种基于划分的动态聚类算法[J]. 计算机工程与设计, 2005, 26(1): 177-179,229
作者姓名:万志华  欧阳为民  张平庸
作者单位:上海大学,计算机工程与科学学院,上海,200072;上海大学,网络中心,上海,200072
摘    要:聚类分析是数据挖掘的一个重要研究分支,已经提出了许多聚类算法,划分方法是其中之一。划分方法的缺点是要求事先给定聚类结果数,对初始划分和输入顺序敏感等。为克服这些缺陷,以划分方法为基础,提出了一种基于划分的动态聚类算法。该算法按密度从大到小,依距离选择较为分散的初始值,同时可以过滤噪声数据,并在聚类的过程中动态地改变聚类结果数,改善了聚类质量,获得了更自然的结果。

关 键 词:聚类  数据挖掘  划分方法  k-means
文章编号:1000-7024(2005)01-0177-03

Partition-based dynamic clustering algorithm
WAN Zhi-hua,OUYANG Wei-min,ZHANG Ping-yong. Partition-based dynamic clustering algorithm[J]. Computer Engineering and Design, 2005, 26(1): 177-179,229
Authors:WAN Zhi-hua  OUYANG Wei-min  ZHANG Ping-yong
Abstract:Clustering is a promising application area for many fields including data mining, statistical data analysis, pattern recognition, image processing, etc. Partitioning method is a clustering algorithm, which is sensible to initial partitions (values of k), initial values and input sequence. To overcome these disadvantages, a partition-based dynamic clustering algorithm is developed. At first, the data objects is sorted by their densities. Then some dispersive data objects is selected as initial cluster centers according to priority. At the same time, the outliers can be filtrated. And it changes the numbers of partitions during the clustering. The experiments demonstrate that the algorithm improves the partition method and gets the better results.
Keywords:clustering  data mining  partition method  k-means
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号